Triple
T14651328
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marché International de Rungis |
E343991
|
entity |
| Predicate | operatedBy |
P86
|
FINISHED |
| Object |
SEMMARIS
SEMMARIS is the semi-public company that manages and develops the Rungis International Market, one of the world’s largest wholesale food markets near Paris.
|
E1112166
|
NE FINISHED |
How this triple was built (4 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: SEMMARIS | Statement: [Marché International de Rungis, operatedBy, SEMMARIS]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SEMMARIS Context triple: [Marché International de Rungis, operatedBy, SEMMARIS]
-
A.
SEMAL
SEMAL is the UN/LOCODE designation for the port and transport location associated with Lake Mälaren in Sweden.
-
B.
Seme
Seme is a border town between Nigeria and Benin that serves as a major West African road crossing and trade route.
-
C.
Semera
Semera is a planned town in northeastern Ethiopia that serves as the administrative and economic center of the Afar Region.
-
D.
Semily
Semily is a small town in the northern Czech Republic known for its location in the Liberec Region near the Bohemian Paradise (Český ráj) landscape area.
-
E.
Semel
Semel is a town in the Dohuk Governorate of the Kurdistan Region in northern Iraq, known for its Assyrian population and the 1933 Simele massacre.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: SEMMARIS Triple: [Marché International de Rungis, operatedBy, SEMMARIS]
Generated description
SEMMARIS is the semi-public company that manages and develops the Rungis International Market, one of the world’s largest wholesale food markets near Paris.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: SEMMARIS Target entity description: SEMMARIS is the semi-public company that manages and develops the Rungis International Market, one of the world’s largest wholesale food markets near Paris.
-
A.
SEMAL
SEMAL is the UN/LOCODE designation for the port and transport location associated with Lake Mälaren in Sweden.
-
B.
Seme
Seme is a border town between Nigeria and Benin that serves as a major West African road crossing and trade route.
-
C.
Semera
Semera is a planned town in northeastern Ethiopia that serves as the administrative and economic center of the Afar Region.
-
D.
Semily
Semily is a small town in the northern Czech Republic known for its location in the Liberec Region near the Bohemian Paradise (Český ráj) landscape area.
-
E.
Semel
Semel is a town in the Dohuk Governorate of the Kurdistan Region in northern Iraq, known for its Assyrian population and the 1933 Simele massacre.
- F. None of above. chosen
Provenance (5 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d822e1a2cc81908e5bb93cf61ce3cc |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb517e7648190b9fc73d6cdbb68de |
completed | April 14, 2026, 9:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fdd5d9ab188190934deb57fd6d9a56 |
completed | May 8, 2026, 12:23 p.m. |
| NEDg | Description generation | batch_69fdd6b2f6148190bb91d55833308d5f |
completed | May 8, 2026, 12:27 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69fdd77fdc608190a89e4dbf5ce4b695 |
completed | May 8, 2026, 12:30 p.m. |
Created at: April 10, 2026, 1:27 a.m.